Abstract
Crack detection is a critical task in routine inspection of building structures. Most of the traditional crack detection methodologies are conducted by human inspectors that may submit inaccurate damage assessments. In recent years, deep learning has produced extremely promising results for various tasks. In this work, a lightweight end-to-end pixel-wise classification architecture called SegNet is employed to segment the structure surface cracks. Compared with other semantic segmentation architectures, SegNet uses pooling indices calculated in the pooling step of the encoder to perform non-linear upsampling in the corresponding decoder, which doesn’t require to learn in the upsample. In this paper, a crack image dataset collected under a variety of complex environment are utilized to train and test the SegNet model, i.e. a self-labeled dataset with 2068 bridge cracks images at the size of \(1024\times 1024\). In order to improve the generalization ability of network data augmentation is used. The experimental results show that the SegNet outperforms the traditional edge detection algorithm, such as Canny and Sobel, in the dataset. The trained SegNet model can be used to segment the cracks in images at any size with the assistant of sliding window scanning technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Schmidt, P., Earthman, J.: Development of a scanning laser crack detection technique for corrosion fatigue testing of fine wire. J. Mater. Res. 10(2), 372–380 (1995)
Tong, C., Wang, W.: Research of detection of a crack on pressure vessel based on both of acoustic emission diagnosis and ultrasonic testing. In: 2011 Second International Conference on Mechanic Automation and Control Engineering, pp. 1510–1513. IEEE (2011)
Fu, Z., et al.: Image segmentation with multilevel threshold of gray-level & gradient-magnitude entropy based on genetic algorithm. In: 2015 International Conference on Artificial Intelligence and Industrial Engineering
Joseph, H., Periyasamy, R.: An analytical method for the adaptive computation of threshold of gradient modulus in 2D anisotropic diffusion filter. Biocybernetics Biomed. Eng. 37(1), 1–10 (2017)
Zhu, C.: A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features. IEEE Trans. Geosci. Remote Sens. 48(9), 3446–3456 (2010)
Ciresan, D.C.: Deep, big, simple neural nets for handwritten digit recognition. Neural Comput. 22(12), 3207–3220 (2010)
Hou, L., Samaras, D., Kurc, T.M., Gao, Y., Davis, J.E., Saltz, J.H.: Patch-based convolutional neural network for whole slide tissue image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2424–2433. IEEE (2016)
Ji, J., Wu, L., Chen, Z., Yu, J., Lin, P., Cheng, S.: Automated pixel-level surface crack detection using U-Net. In: International Conference on Multi-disciplinary Trends in Artificial Intelligence, pp. 69–78. IEEE (2018)
Wang, X., Hu, Z.: Grid-based pavement crack analysis using deep learning. In: 2017 4th International Conference on Transportation Information and Safety (ICTIS), pp. 917–924. IEEE (2017)
Zhang, A.: Deep learning-based fully automated pavement crack detection on 3D asphalt surfaces with an improved CrackNet. J. Comput. Civil Eng. 32(5), 04018041 (2008)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440. IEEE (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241. IEEE (2015)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708. IEEE (2017)
Badrinarayanan, V., Handa, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Ma, W.F.: Research on Bridge Crack Detection Algorithm Based on Deep Learning. MS thesis, Shaanxi Normal University (2018). (in Chinese)
Acknowledgements
This work is financially supported in parts by the Fujian Provincial Department of Science and Technology of China (Grant No. 2019H0006 and 2018J01774), the National Natural Science Foundation of China (Grant No. 61601127), and the Foundation of Fujian Provincial Department of Industry and Information Technology of China (Grant No. 82318075).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Song, C. et al. (2019). Pixel-Level Crack Detection in Images Using SegNet. In: Chamchong, R., Wong, K. (eds) Multi-disciplinary Trends in Artificial Intelligence. MIWAI 2019. Lecture Notes in Computer Science(), vol 11909. Springer, Cham. https://doi.org/10.1007/978-3-030-33709-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-33709-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33708-7
Online ISBN: 978-3-030-33709-4
eBook Packages: Computer ScienceComputer Science (R0)